© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 13-GEMMASCOPE-RES-16K
    11. 7072
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and terms related to proofs and theorems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cristales
    -0.40
     väli
    -0.36
    cifix
    -0.36
     vorg
    -0.36
     prédé
    -0.35
    WriteTagHelper
    -0.34
     aikaa
    -0.34
    \{\\
    -0.33
    itiva
    -0.33
     tepat
    -0.32
    POSITIVE LOGITS
     дописавши
    1.02
    StructEnd
    0.84
     kasarigan
    0.83
     tartalomajánló
    0.79
    featureID
    0.75
    expandindo
    0.69
    Portail
    0.65
    Portale
    0.62
    exitRule
    0.60
     estekak
    0.57
    Activations Density 0.685%

    No Known Activations